Refusals (LLM Leaderboard)
Leaderboard of refusal rates across the GPT-4o, o1-mini, o1-preview, and Claude 3.5 Sonnet language models. Comparative analysis of how different …
A Spooky Tale of ChatGPT – The Error That Won't Go Away
How I lost hours of my life by blindly trusting ChatGPT.
Custom LLM as a Judge to Detect Hallucinations with Braintrust
<p>Article URL: <a …
Hacking Back the AI-Hacker: Prompt Injection as a Defense for LLM-Attackers
Large language models (LLMs) are increasingly being harnessed to automate cyberattacks, making sophisticated exploits more accessible and scalable. In …
LLM Code Generation with Formal Specifications and Reactive Program Synthesis
In the past few years, Large Language Models (LLMs) have exploded in usefulness and popularity for code generation tasks. However, LLMs still struggle …
Improving earthquake prediction accuracy in Los Angeles with machine learning
This research breaks new ground in earthquake prediction for Los Angeles, California, by leveraging advanced machine learning and neural network …
Natural Language Outlines for Code: Literate Programming in the LLM Era
We propose using natural language outlines as a novel modality and interaction surface for providing AI assistance to developers throughout the …
How a Mumbai Drugmaker Is Helping Putin Get Nvidia AI Chips
Trade-tracking data show that the Indian firm is selling top-end Dell servers optimized for artificial intelligence to Russia.
Microsoft AI Recorder Competitor
General Bots tools running on Desktop. Contribute to GeneralBots/BotDesktop development by creating an account on GitHub.
AI-based medical transcription tool hallucinates, raises concerns
A good transcription app shouldn't indulge in creative writing.
ChatGPT advanced voice mode can attempt Spanish with a Russian accent
ChatGPT advanced voice mode may refuse to sing (unless you jailbreak it) but it's quite happy to attempt different accents. I've been having a _lot_ …
Easy Way to Generate Complete Project Source Code with ChatGPT / Claude.ai
While it’s straightforward to create a single file using AI, generating an entire project structure can be more challenging. For example…